Qwen2.5 1.5B DPO Tulu3 Decontaminated is an open-source language model by ali-elganzory. Features: 8b LLM, VRAM: 3.1GB, Context: 128K, LLM Explorer Score: 0.23.
Arxiv:2305.18290 Base model:ali-elganzory/qwen2... Base model:finetune:ali-elganz... Conversational Dpo Endpoints compatible Generated from trainer Qwen2 Region:us Safetensors Trl
Model Card on HF 🤗: https://huggingface.co/ali-elganzory/Qwen2.5-1.5B-DPO-Tulu3-decontaminated
Qwen2.5 1.5B DPO Tulu3 Decontaminated Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen2.5 1.5B DPO Tulu3 Decontaminated Parameters and Internals
| LLM Name | Qwen2.5 1.5B DPO Tulu3 Decontaminated |
| Repository 🤗 | https://huggingface.co/ali-elganzory/Qwen2.5-1.5B-DPO-Tulu3-decontaminated |
| Model Name | ali-elganzory-Qwen2.5-1.5B-SFT-Tulu3-decontaminated_tulu-3-8b-preference-mixture-decontaminated_GH200 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 3.1 GB |
| Updated | 2026-05-04 |
| Maintainer | ali-elganzory |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.57.6 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151680 |
| Errors | replace |
Best Alternatives to Qwen2.5 1.5B DPO Tulu3 Decontaminated
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SJT 8B | 128K / 17.8 GB | 13 | 1 |
| Sailor2 L 8B | 128K / 17.1 GB | 6 | 0 |
| Sailor2 8B Chat | 4K / 17.1 GB | 361 | 19 |
| SupaMATH | 128K / 5.6 GB | 5 | 0 |
| BloomVN 8B Chat | 32K / 17.1 GB | 3 | 5 |
| Sailor2 8B Chat Uncensored | 32K / 17.1 GB | 10 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than ali-elganzory/Qwen2.5-1.5B-DPO-Tulu3-decontaminated .
Rank the Qwen2.5 1.5B DPO Tulu3 Decontaminated Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53972 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a